Deep Learning for chaos detection.

In this article, we study how a chaos detection problem can be solved using Deep Learning techniques. We consider two classical test examples: the Logistic map as a discrete dynamical system and the Lorenz system as a continuous dynamical system. We train three types of artificial neural networks (multi-layer perceptron, convolutional neural network, and long short-term memory cell) to classify time series from the mentioned systems into regular or chaotic. This approach allows us to study biparametric and triparametric regions in the Lorenz system due to their low computational cost compared to traditional techniques.

[1]  M. Vasile,et al.  Classification of regular and chaotic motions in Hamiltonian systems with deep learning , 2022, Scientific Reports.

[2]  Rohitash Chandra,et al.  Evaluation of Deep Learning Models for Multi-Step Ahead Time Series Prediction , 2021, IEEE Access.

[3]  Woo Seok Lee,et al.  Deep learning of chaos classification , 2020, Mach. Learn. Sci. Technol..

[4]  Jaideep Pathak,et al.  Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics , 2019, Neural Networks.

[5]  Y. Nakatsukasa,et al.  Classification of chaotic time series with deep learning , 2019, Physica D: Nonlinear Phenomena.

[6]  Desmond J. Higham,et al.  Edinburgh Research Explorer Deep learning: an introduction for applied mathematicians , 2022 .

[7]  Bernd Krauskopf,et al.  Global invariant manifolds in the transition to preturbulence in the Lorenz system , 2011 .

[8]  J Bragard,et al.  Chaotic dynamics of a magnetic nanoparticle. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Roberto Barrio,et al.  Bounds for the chaotic region in the Lorenz model , 2009 .

[10]  Roberto Barrio,et al.  A three-parametric study of the Lorenz model , 2007 .

[11]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[12]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[13]  Robert M. May,et al.  Simple mathematical models with very complicated dynamics , 1976, Nature.

[14]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .